+
+ if (ndev->pw_mode == target)
+ return 0;
+
+ switch (target) {
+ case POWER_MODE_TURBO:
+ if (ndev->hwctx_num) {
+ XDNA_ERR(xdna, "Can not set turbo when there is active
hwctx");
+ return -EINVAL;
+ }
+
+ clk_gating = AIE2_CLK_GATING_DISABLE;
+ dpm_level = ndev->max_dpm_level;
+ break;
+ case POWER_MODE_HIGH:
+ clk_gating = AIE2_CLK_GATING_ENABLE;
+ dpm_level = ndev->max_dpm_level;
+ break;
+ case POWER_MODE_DEFAULT:
+ clk_gating = AIE2_CLK_GATING_ENABLE;
+ dpm_level = ndev->dft_dpm_level;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ ret = ndev->priv->hw_ops.set_dpm(ndev, dpm_level);
+ if (ret)
+ return ret;
+
+ ret = aie2_pm_set_clk_gating(ndev, clk_gating);
+ if (ret)
+ return ret;
+
+ ndev->pw_mode = target;
+
+ return 0;
+}
diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/
amdxdna/aie2_smu.c
index 91893d438da7..73388443c676 100644
--- a/drivers/accel/amdxdna/aie2_smu.c
+++ b/drivers/accel/amdxdna/aie2_smu.c
@@ -19,8 +19,11 @@
#define AIE2_SMU_POWER_OFF 0x4
#define AIE2_SMU_SET_MPNPUCLK_FREQ 0x5
#define AIE2_SMU_SET_HCLK_FREQ 0x6
+#define AIE2_SMU_SET_SOFT_DPMLEVEL 0x7
+#define AIE2_SMU_SET_HARD_DPMLEVEL 0x8
-static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32
reg_cmd, u32 reg_arg)
+static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd,
+ u32 reg_arg, u32 *out)
{
u32 resp;
int ret;
@@ -40,6 +43,9 @@ static int aie2_smu_exec(struct amdxdna_dev_hdl
*ndev, u32 reg_cmd, u32 reg_arg)
return ret;
}
+ if (out)
+ *out = readl(SMU_REG(ndev, SMU_OUT_REG));
+
if (resp != SMU_RESULT_OK) {
XDNA_ERR(ndev->xdna, "smu cmd %d failed, 0x%x", reg_cmd,
resp);
return -EINVAL;
@@ -48,63 +54,71 @@ static int aie2_smu_exec(struct amdxdna_dev_hdl
*ndev, u32 reg_cmd, u32 reg_arg)
return 0;
}
-static int aie2_smu_set_mpnpu_clock_freq(struct amdxdna_dev_hdl
*ndev, u32 freq_mhz)
+int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
{
+ u32 freq;
int ret;
- if (!freq_mhz || freq_mhz > SMU_MPNPUCLK_FREQ_MAX(ndev)) {
- XDNA_ERR(ndev->xdna, "invalid mpnpu clock freq %d", freq_mhz);
- return -EINVAL;
+ ret = aie2_smu_exec(ndev, AIE2_SMU_SET_MPNPUCLK_FREQ,
+ ndev->priv->dpm_clk_tbl[dpm_level].npuclk, &freq);
+ if (ret) {
+ XDNA_ERR(ndev->xdna, "Set npu clock to %d failed, ret %d\n",
+ ndev->priv->dpm_clk_tbl[dpm_level].npuclk, ret);
}
+ ndev->npuclk_freq = freq;
- ndev->mp_npu_clock.freq_mhz = freq_mhz;
- ret = aie2_smu_exec(ndev, AIE2_SMU_SET_MPNPUCLK_FREQ, freq_mhz);
- if (!ret)
- XDNA_INFO_ONCE(ndev->xdna, "set mpnpu_clock = %d mhz",
freq_mhz);
-
- return ret;
-}
-
-static int aie2_smu_set_hclock_freq(struct amdxdna_dev_hdl *ndev,
u32 freq_mhz)
-{
- int ret;
-
- if (!freq_mhz || freq_mhz > SMU_HCLK_FREQ_MAX(ndev)) {
- XDNA_ERR(ndev->xdna, "invalid hclock freq %d", freq_mhz);
- return -EINVAL;
+ ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HCLK_FREQ,
+ ndev->priv->dpm_clk_tbl[dpm_level].hclk, &freq);
+ if (ret) {
+ XDNA_ERR(ndev->xdna, "Set h clock to %d failed, ret %d\n",
+ ndev->priv->dpm_clk_tbl[dpm_level].hclk, ret);
}
+ ndev->hclk_freq = freq;
+ ndev->dpm_level = dpm_level;
- ndev->h_clock.freq_mhz = freq_mhz;
- ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HCLK_FREQ, freq_mhz);
- if (!ret)
- XDNA_INFO_ONCE(ndev->xdna, "set npu_hclock = %d mhz",
freq_mhz);
+ XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n",
+ ndev->npuclk_freq, ndev->hclk_freq);
- return ret;
+ return 0;
}
-int aie2_smu_init(struct amdxdna_dev_hdl *ndev)
+int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
{
int ret;
- ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_ON, 0);
+ ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HARD_DPMLEVEL, dpm_level,
NULL);
if (ret) {
- XDNA_ERR(ndev->xdna, "Power on failed, ret %d", ret);
+ XDNA_ERR(ndev->xdna, "Set hard dpm level %d failed, ret %d ",
+ dpm_level, ret);
return ret;
}
- ret = aie2_smu_set_mpnpu_clock_freq(ndev,
SMU_MPNPUCLK_FREQ_MAX(ndev));
+ ret = aie2_smu_exec(ndev, AIE2_SMU_SET_SOFT_DPMLEVEL, dpm_level,
NULL);
if (ret) {
- XDNA_ERR(ndev->xdna, "Set mpnpu clk freq failed, ret %d", ret);
+ XDNA_ERR(ndev->xdna, "Set soft dpm level %d failed, ret %d",
+ dpm_level, ret);
return ret;
}
- snprintf(ndev->mp_npu_clock.name, sizeof(ndev-
>mp_npu_clock.name), "MP-NPU Clock");
- ret = aie2_smu_set_hclock_freq(ndev, SMU_HCLK_FREQ_MAX(ndev));
+ ndev->npuclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].npuclk;
+ ndev->hclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].hclk;
+ ndev->dpm_level = dpm_level;
+
+ XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n",
+ ndev->npuclk_freq, ndev->hclk_freq);
+
+ return 0;
+}
+
+int aie2_smu_init(struct amdxdna_dev_hdl *ndev)
+{
+ int ret;
+
+ ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_ON, 0, NULL);
if (ret) {
- XDNA_ERR(ndev->xdna, "Set hclk freq failed, ret %d", ret);
+ XDNA_ERR(ndev->xdna, "Power on failed, ret %d", ret);
return ret;
}
- snprintf(ndev->h_clock.name, sizeof(ndev->h_clock.name), "H
Clock");
return 0;
}
@@ -113,7 +127,8 @@ void aie2_smu_fini(struct amdxdna_dev_hdl *ndev)
{
int ret;
- ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_OFF, 0);
+ ndev->priv->hw_ops.set_dpm(ndev, 0);
+ ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_OFF, 0, NULL);
if (ret)
XDNA_ERR(ndev->xdna, "Power off failed, ret %d", ret);
}
diff --git a/drivers/accel/amdxdna/aie2_solver.c b/drivers/accel/
amdxdna/aie2_solver.c
index a537c66589a4..1939625d6027 100644
--- a/drivers/accel/amdxdna/aie2_solver.c
+++ b/drivers/accel/amdxdna/aie2_solver.c
@@ -25,6 +25,7 @@ struct solver_node {
struct partition_node *pt_node;
void *cb_arg;
+ u32 dpm_level;
u32 cols_len;
u32 start_cols[] __counted_by(cols_len);
};
@@ -95,6 +96,51 @@ static int sanity_check(struct solver_state *xrs,
struct alloc_requests *req)
return 0;
}
+static bool is_valid_qos_dpm_params(struct aie_qos *rqos)
+{
+ /*
+ * gops is retrieved from the xmodel, so it's always set
+ * fps and latency are the configurable params from the application
+ */
+ if (rqos->gops > 0 && (rqos->fps > 0 || rqos->latency > 0))
+ return true;
+
+ return false;
+}
+
+static int set_dpm_level(struct solver_state *xrs, struct
alloc_requests *req, u32 *dpm_level)
+{
+ struct solver_rgroup *rgp = &xrs->rgp;
+ struct cdo_parts *cdop = &req->cdo;
+ struct aie_qos *rqos = &req->rqos;
+ u32 freq, max_dpm_level, level;
+ struct solver_node *node;
+
+ max_dpm_level = xrs->cfg.clk_list.num_levels - 1;
+ /* If no QoS parameters are passed, set it to the max DPM level */
+ if (!is_valid_qos_dpm_params(rqos)) {
+ level = max_dpm_level;
+ goto set_dpm;
+ }
+
+ /* Find one CDO group that meet the GOPs requirement. */
+ for (level = 0; level < max_dpm_level; level++) {
+ freq = xrs->cfg.clk_list.cu_clk_list[level];
+ if (!qos_meet(xrs, rqos, cdop->qos_cap.opc * freq / 1000))
+ break;
+ }
+
+ /* set the dpm level which fits all the sessions */
+ list_for_each_entry(node, &rgp->node_list, list) {
+ if (node->dpm_level > level)
+ level = node->dpm_level;
+ }
+
+set_dpm:
+ *dpm_level = level;
+ return xrs->cfg.actions->set_dft_dpm_level(xrs->cfg.ddev, level);
+}
+
static struct solver_node *rg_search_node(struct solver_rgroup
*rgp, u64 rid)
{
struct solver_node *node;
@@ -159,12 +205,9 @@ static int get_free_partition(struct
solver_state *xrs,
pt_node->ncols = ncols;
/*
- * Before fully support latency in QoS, if a request
- * specifies a non-zero latency value, it will not share
- * the partition with other requests.
+ * Always set exclusive to false for now.
*/
- if (req->rqos.latency)
- pt_node->exclusive = true;
+ pt_node->exclusive = false;
list_add_tail(&pt_node->list, &xrs->rgp.pt_node_list);
xrs->rgp.npartition_node++;
@@ -257,6 +300,7 @@ int xrs_allocate_resource(void *hdl, struct
alloc_requests *req, void *cb_arg)
struct xrs_action_load load_act;
struct solver_node *snode;
struct solver_state *xrs;
+ u32 dpm_level;
int ret;
xrs = (struct solver_state *)hdl;
@@ -281,6 +325,11 @@ int xrs_allocate_resource(void *hdl, struct
alloc_requests *req, void *cb_arg)
if (ret)
goto free_node;
+ ret = set_dpm_level(xrs, req, &dpm_level);
+ if (ret)
+ goto free_node;
+
+ snode->dpm_level = dpm_level;
snode->cb_arg = cb_arg;
drm_dbg(xrs->cfg.ddev, "start col %d ncols %d\n",
diff --git a/drivers/accel/amdxdna/aie2_solver.h b/drivers/accel/
amdxdna/aie2_solver.h
index 9b1847bb46a6..a2e3c52229e9 100644
--- a/drivers/accel/amdxdna/aie2_solver.h
+++ b/drivers/accel/amdxdna/aie2_solver.h
@@ -99,6 +99,7 @@ struct clk_list_info {
struct xrs_action_ops {
int (*load)(void *cb_arg, struct xrs_action_load *action);
int (*unload)(void *cb_arg);
+ int (*set_dft_dpm_level)(struct drm_device *ddev, u32 level);
};
/*
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/
amdxdna/amdxdna_pci_drv.c
index c3541796d189..6bbd437d48d8 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -160,6 +160,24 @@ static int amdxdna_drm_get_info_ioctl(struct
drm_device *dev, void *data, struct
return ret;
}
+static int amdxdna_drm_set_state_ioctl(struct drm_device *dev,
void *data, struct drm_file *filp)
+{
+ struct amdxdna_client *client = filp->driver_priv;
+ struct amdxdna_dev *xdna = to_xdna_dev(dev);
+ struct amdxdna_drm_set_state *args = data;
+ int ret;
+
+ if (!xdna->dev_info->ops->set_aie_state)
+ return -EOPNOTSUPP;
+
+ XDNA_DBG(xdna, "Request parameter %u", args->param);
+ mutex_lock(&xdna->dev_lock);
+ ret = xdna->dev_info->ops->set_aie_state(client, args);
+ mutex_unlock(&xdna->dev_lock);
+
+ return ret;
+}
+
static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = {
/* Context */
DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX,
amdxdna_drm_create_hwctx_ioctl, 0),
@@ -173,6 +191,7 @@ static const struct drm_ioctl_desc
amdxdna_drm_ioctls[] = {
DRM_IOCTL_DEF_DRV(AMDXDNA_EXEC_CMD,
amdxdna_drm_submit_cmd_ioctl, 0),
/* AIE hardware */
DRM_IOCTL_DEF_DRV(AMDXDNA_GET_INFO, amdxdna_drm_get_info_ioctl,
0),
+ DRM_IOCTL_DEF_DRV(AMDXDNA_SET_STATE,
amdxdna_drm_set_state_ioctl, DRM_ROOT_ONLY),
};
static const struct file_operations amdxdna_fops = {
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/
amdxdna/amdxdna_pci_drv.h
index f5b830fb14bb..e2071e31d949 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.h
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -20,6 +20,7 @@ extern const struct drm_driver amdxdna_drm_drv;
struct amdxdna_client;
struct amdxdna_dev;
struct amdxdna_drm_get_info;
+struct amdxdna_drm_set_state;
struct amdxdna_gem_obj;
struct amdxdna_hwctx;
struct amdxdna_sched_job;
@@ -40,6 +41,7 @@ struct amdxdna_dev_ops {
void (*hwctx_resume)(struct amdxdna_hwctx *hwctx);
int (*cmd_submit)(struct amdxdna_hwctx *hwctx, struct
amdxdna_sched_job *job, u64 *seq);
int (*get_aie_info)(struct amdxdna_client *client, struct
amdxdna_drm_get_info *args);
+ int (*set_aie_state)(struct amdxdna_client *client, struct
amdxdna_drm_set_state *args);
};
/*
diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/
amdxdna/npu1_regs.c
index f00c50461b09..c8f4d1cac65d 100644
--- a/drivers/accel/amdxdna/npu1_regs.c
+++ b/drivers/accel/amdxdna/npu1_regs.c
@@ -44,18 +44,30 @@
#define NPU1_SMU_BAR_BASE MPNPU_APERTURE0_BASE
#define NPU1_SRAM_BAR_BASE MPNPU_APERTURE1_BASE
-#define NPU1_RT_CFG_TYPE_PDI_LOAD 2
-#define NPU1_RT_CFG_VAL_PDI_LOAD_MGMT 0
-#define NPU1_RT_CFG_VAL_PDI_LOAD_APP 1
+const struct rt_config npu1_default_rt_cfg[] = {
+ { 2, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */
+ { 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+ { 0 },
+};
-#define NPU1_MPNPUCLK_FREQ_MAX 600
-#define NPU1_HCLK_FREQ_MAX 1024
+const struct dpm_clk_freq npu1_dpm_clk_table[] = {
+ {400, 800},
+ {600, 1024},
+ {600, 1024},
+ {600, 1024},
+ {600, 1024},
+ {720, 1309},
+ {720, 1309},
+ {847, 1600},
+ { 0 }
+};
const struct amdxdna_dev_priv npu1_dev_priv = {
.fw_path = "amdnpu/1502_00/npu.sbin",
.protocol_major = 0x5,
.protocol_minor = 0x1,
- .rt_config = {NPU1_RT_CFG_TYPE_PDI_LOAD,
NPU1_RT_CFG_VAL_PDI_LOAD_APP},
+ .rt_config = npu1_default_rt_cfg,
+ .dpm_clk_tbl = npu1_dpm_clk_table,
.col_align = COL_ALIGN_NONE,
.mbox_dev_addr = NPU1_MBOX_BAR_BASE,
.mbox_size = 0, /* Use BAR size */
@@ -80,8 +92,9 @@ const struct amdxdna_dev_priv npu1_dev_priv = {
DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU1_SMU, MPNPU_PUB_SCRATCH6),
DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU1_SMU, MPNPU_PUB_SCRATCH7),
},
- .smu_mpnpuclk_freq_max = NPU1_MPNPUCLK_FREQ_MAX,
- .smu_hclk_freq_max = NPU1_HCLK_FREQ_MAX,
+ .hw_ops = {
+ .set_dpm = npu1_set_dpm,
+ },
};
const struct amdxdna_dev_info dev_npu1_info = {
diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/
amdxdna/npu2_regs.c
index 00cb381031d2..ac63131f9c7c 100644
--- a/drivers/accel/amdxdna/npu2_regs.c
+++ b/drivers/accel/amdxdna/npu2_regs.c
@@ -61,18 +61,12 @@
#define NPU2_SMU_BAR_BASE MMNPU_APERTURE4_BASE
#define NPU2_SRAM_BAR_BASE MMNPU_APERTURE1_BASE
-#define NPU2_RT_CFG_TYPE_PDI_LOAD 5
-#define NPU2_RT_CFG_VAL_PDI_LOAD_MGMT 0
-#define NPU2_RT_CFG_VAL_PDI_LOAD_APP 1
-
-#define NPU2_MPNPUCLK_FREQ_MAX 1267
-#define NPU2_HCLK_FREQ_MAX 1800
-
const struct amdxdna_dev_priv npu2_dev_priv = {
.fw_path = "amdnpu/17f0_00/npu.sbin",
.protocol_major = 0x6,
.protocol_minor = 0x1,
- .rt_config = {NPU2_RT_CFG_TYPE_PDI_LOAD,
NPU2_RT_CFG_VAL_PDI_LOAD_APP},
+ .rt_config = npu4_default_rt_cfg,
+ .dpm_clk_tbl = npu4_dpm_clk_table,
.col_align = COL_ALIGN_NATURE,
.mbox_dev_addr = NPU2_MBOX_BAR_BASE,
.mbox_size = 0, /* Use BAR size */
@@ -97,8 +91,9 @@ const struct amdxdna_dev_priv npu2_dev_priv = {
DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU2_SMU, MP1_C2PMSG_61),
DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU2_SMU, MP1_C2PMSG_60),
},
- .smu_mpnpuclk_freq_max = NPU2_MPNPUCLK_FREQ_MAX,
- .smu_hclk_freq_max = NPU2_HCLK_FREQ_MAX,
+ .hw_ops = {
+ .set_dpm = npu4_set_dpm,
+ },
};
const struct amdxdna_dev_info dev_npu2_info = {
diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/
amdxdna/npu4_regs.c
index b6dae9667cca..a713ac18adfc 100644
--- a/drivers/accel/amdxdna/npu4_regs.c
+++ b/drivers/accel/amdxdna/npu4_regs.c
@@ -61,18 +61,33 @@
#define NPU4_SMU_BAR_BASE MMNPU_APERTURE4_BASE
#define NPU4_SRAM_BAR_BASE MMNPU_APERTURE1_BASE
-#define NPU4_RT_CFG_TYPE_PDI_LOAD 5
-#define NPU4_RT_CFG_VAL_PDI_LOAD_MGMT 0
-#define NPU4_RT_CFG_VAL_PDI_LOAD_APP 1
+const struct rt_config npu4_default_rt_cfg[] = {
+ { 5, 1, AIE2_RT_CFG_INIT }, /* PDI APP LOAD MODE */
+ { 1, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+ { 2, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+ { 3, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+ { 4, 1, AIE2_RT_CFG_CLK_GATING }, /* Clock gating on */
+ { 0 },
+};
-#define NPU4_MPNPUCLK_FREQ_MAX 1267
-#define NPU4_HCLK_FREQ_MAX 1800
+const struct dpm_clk_freq npu4_dpm_clk_table[] = {
+ {396, 792},
+ {600, 1056},
+ {792, 1152},
+ {975, 1267},
+ {975, 1267},
+ {1056, 1408},
+ {1152, 1584},
+ {1267, 1800},
+ { 0 }
+};
const struct amdxdna_dev_priv npu4_dev_priv = {
.fw_path = "amdnpu/17f0_10/npu.sbin",
.protocol_major = 0x6,
.protocol_minor = 0x1,
- .rt_config = {NPU4_RT_CFG_TYPE_PDI_LOAD,
NPU4_RT_CFG_VAL_PDI_LOAD_APP},
+ .rt_config = npu4_default_rt_cfg,
+ .dpm_clk_tbl = npu4_dpm_clk_table,
.col_align = COL_ALIGN_NATURE,
.mbox_dev_addr = NPU4_MBOX_BAR_BASE,
.mbox_size = 0, /* Use BAR size */
@@ -97,8 +112,9 @@ const struct amdxdna_dev_priv npu4_dev_priv = {
DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU4_SMU, MP1_C2PMSG_61),
DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU4_SMU, MP1_C2PMSG_60),
},
- .smu_mpnpuclk_freq_max = NPU4_MPNPUCLK_FREQ_MAX,
- .smu_hclk_freq_max = NPU4_HCLK_FREQ_MAX,
+ .hw_ops = {
+ .set_dpm = npu4_set_dpm,
+ },
};
const struct amdxdna_dev_info dev_npu4_info = {
diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/
amdxdna/npu5_regs.c
index bed1baf8e160..67a5d5bc8a49 100644
--- a/drivers/accel/amdxdna/npu5_regs.c
+++ b/drivers/accel/amdxdna/npu5_regs.c
@@ -61,18 +61,12 @@
#define NPU5_SMU_BAR_BASE MMNPU_APERTURE4_BASE
#define NPU5_SRAM_BAR_BASE MMNPU_APERTURE1_BASE
-#define NPU5_RT_CFG_TYPE_PDI_LOAD 5
-#define NPU5_RT_CFG_VAL_PDI_LOAD_MGMT 0
-#define NPU5_RT_CFG_VAL_PDI_LOAD_APP 1
-
-#define NPU5_MPNPUCLK_FREQ_MAX 1267
-#define NPU5_HCLK_FREQ_MAX 1800
-
const struct amdxdna_dev_priv npu5_dev_priv = {
.fw_path = "amdnpu/17f0_11/npu.sbin",
.protocol_major = 0x6,
.protocol_minor = 0x1,
- .rt_config = {NPU5_RT_CFG_TYPE_PDI_LOAD,
NPU5_RT_CFG_VAL_PDI_LOAD_APP},
+ .rt_config = npu4_default_rt_cfg,
+ .dpm_clk_tbl = npu4_dpm_clk_table,
.col_align = COL_ALIGN_NATURE,
.mbox_dev_addr = NPU5_MBOX_BAR_BASE,
.mbox_size = 0, /* Use BAR size */
@@ -97,8 +91,9 @@ const struct amdxdna_dev_priv npu5_dev_priv = {
DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU5_SMU, MP1_C2PMSG_61),
DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU5_SMU, MP1_C2PMSG_60),
},
- .smu_mpnpuclk_freq_max = NPU5_MPNPUCLK_FREQ_MAX,
- .smu_hclk_freq_max = NPU5_HCLK_FREQ_MAX,
+ .hw_ops = {
+ .set_dpm = npu4_set_dpm,
+ },
};
const struct amdxdna_dev_info dev_npu5_info = {
diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/
amdxdna/npu6_regs.c
index d1168fc55533..f46c760cefc7 100644
--- a/drivers/accel/amdxdna/npu6_regs.c
+++ b/drivers/accel/amdxdna/npu6_regs.c
@@ -61,23 +61,12 @@
#define NPU6_SMU_BAR_BASE MMNPU_APERTURE4_BASE
#define NPU6_SRAM_BAR_BASE MMNPU_APERTURE1_BASE
-#define NPU6_RT_CFG_TYPE_PDI_LOAD 5
-#define NPU6_RT_CFG_TYPE_DEBUG_BO 10
-
-#define NPU6_RT_CFG_VAL_PDI_LOAD_MGMT 0
-#define NPU6_RT_CFG_VAL_PDI_LOAD_APP 1
-
-#define NPU6_RT_CFG_VAL_DEBUG_BO_DEFAULT 0
-#define NPU6_RT_CFG_VAL_DEBUG_BO_LARGE 1
-
-#define NPU6_MPNPUCLK_FREQ_MAX 1267
-#define NPU6_HCLK_FREQ_MAX 1800
-
const struct amdxdna_dev_priv npu6_dev_priv = {
.fw_path = "amdnpu/17f0_10/npu.sbin",
.protocol_major = 0x6,
.protocol_minor = 12,
- .rt_config = {NPU6_RT_CFG_TYPE_PDI_LOAD,
NPU6_RT_CFG_VAL_PDI_LOAD_APP},
+ .rt_config = npu4_default_rt_cfg,
+ .dpm_clk_tbl = npu4_dpm_clk_table,
.col_align = COL_ALIGN_NATURE,
.mbox_dev_addr = NPU6_MBOX_BAR_BASE,
.mbox_size = 0, /* Use BAR size */
@@ -102,6 +91,10 @@ const struct amdxdna_dev_priv npu6_dev_priv = {
DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU6_SMU, MP1_C2PMSG_61),
DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU6_SMU, MP1_C2PMSG_60),
},
+ .hw_ops = {
+ .set_dpm = npu4_set_dpm,
+ },
+
};
const struct amdxdna_dev_info dev_npu6_info = {
diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/
amdxdna_accel.h
index 4f15e53a548d..9af9302baf90 100644
--- a/include/uapi/drm/amdxdna_accel.h
+++ b/include/uapi/drm/amdxdna_accel.h
@@ -33,6 +33,7 @@ enum amdxdna_drm_ioctl_id {
DRM_AMDXDNA_SYNC_BO,
DRM_AMDXDNA_EXEC_CMD,
DRM_AMDXDNA_GET_INFO,
+ DRM_AMDXDNA_SET_STATE,
};
/**
@@ -375,6 +376,24 @@ struct amdxdna_drm_query_hwctx {
__u64 errors;
};
+enum amdxdna_power_mode_type {
+ POWER_MODE_DEFAULT, /* Fallback to calculated DPM */
+ POWER_MODE_LOW, /* Set frequency to lowest DPM */
+ POWER_MODE_MEDIUM, /* Set frequency to medium DPM */
+ POWER_MODE_HIGH, /* Set frequency to highest DPM */
+ POWER_MODE_TURBO, /* Maximum power */
+};
+
+/**
+ * struct amdxdna_drm_get_power_mode - Get the configured power mode
+ * @power_mode: The mode type from enum amdxdna_power_mode_type
+ * @pad: MBZ.
+ */
+struct amdxdna_drm_get_power_mode {
+ __u8 power_mode;
+ __u8 pad[7];
+};
+
/**
* struct amdxdna_drm_query_firmware_version - Query the firmware
version
* @major: The major version number
@@ -397,6 +416,7 @@ enum amdxdna_drm_get_param {
DRM_AMDXDNA_QUERY_SENSORS,
DRM_AMDXDNA_QUERY_HW_CONTEXTS,
DRM_AMDXDNA_QUERY_FIRMWARE_VERSION = 8,
+ DRM_AMDXDNA_GET_POWER_MODE,
};
/**
@@ -411,6 +431,34 @@ struct amdxdna_drm_get_info {
__u64 buffer; /* in/out */
};
+enum amdxdna_drm_set_param {
+ DRM_AMDXDNA_SET_POWER_MODE,
+ DRM_AMDXDNA_WRITE_AIE_MEM,
+ DRM_AMDXDNA_WRITE_AIE_REG,
+};
+
+/**
+ * struct amdxdna_drm_set_state - Set the state of the AIE hardware.
+ * @param: Value in enum amdxdna_drm_set_param.
+ * @buffer_size: Size of the input param.
+ * @buffer: Input param.
+ */
+struct amdxdna_drm_set_state {
+ __u32 param; /* in */
+ __u32 buffer_size; /* in */
+ __u64 buffer; /* in */
+};
+
+/**
+ * struct amdxdna_drm_set_power_mode - Set the power mode of the AIE
hardware
+ * @power_mode: The sensor type from enum amdxdna_power_mode_type
+ * @pad: MBZ.
+ */
+struct amdxdna_drm_set_power_mode {
+ __u8 power_mode;
+ __u8 pad[7];
+};
+
#define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \
DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \
struct amdxdna_drm_create_hwctx)
@@ -443,6 +491,10 @@ struct amdxdna_drm_get_info {
DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_INFO, \
struct amdxdna_drm_get_info)
+#define DRM_IOCTL_AMDXDNA_SET_STATE \
+ DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_SET_STATE, \
+ struct amdxdna_drm_set_state)
+
#if defined(__cplusplus)
} /* extern c end */
#endif
